© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6687
    Prev
    Next
    INDEX
    Explanations

    phrases related to misinformation or misinterpretation

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "mis" indicating wrongdoing or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetti
    -0.77
    ¯¯¯¯
    -0.70
    jriwal
    -0.65
    INGS
    -0.65
    uesday
    -0.63
    ILA
    -0.62
     Norn
    -0.61
     unto
    -0.61
    loo
    -0.60
     Dynamics
    -0.59
    POSITIVE LOGITS
    cellaneous
    1.21
    appropri
    1.16
    pell
    1.04
    beh
    0.98
    pelled
    0.93
    aligned
    0.92
    informed
    0.91
    jud
    0.90
    behavior
    0.87
    anthrop
    0.86
    Activations Density 0.013%

    No Known Activations